docs: Fixed broken links (#1124)

2026-09-25 22:18:30 +02:00 · 2024-08-29 19:19:43 +05:30
parent 92c2f11cec
commit df1d5d6508
6 changed files with 26 additions and 12 deletions
@@ -58,7 +58,7 @@ The illustration below depicts how we can leverage a RAG Evaluation framework to

 ![qdrant_and_quotient.png](/articles_data/rapid-rag-optimization-with-qdrant-and-quotient/qdrant_and_quotient.png)

-We are going to build a RAG application using Qdrant’s Documentation and the premeditated [hugging face dataset]([https://huggingface.co/datasets/atitaarora/qdrant_doc](https://huggingface.co/datasets/atitaarora/qdrant_doc)).
+We are going to build a RAG application using Qdrant’s Documentation and the premeditated [hugging face dataset](https://huggingface.co/datasets/atitaarora/qdrant_doc).
 We will then assess our RAG application’s ability to answer questions about Qdrant.

 To prepare our knowledge store we will use Qdrant, which can be leveraged in 3 different ways as below : 
@@ -89,7 +89,7 @@ COLLECTION_NAME = "qdrant-docs-quotient"

 In this case , we may need to create different collections based on the experiments we conduct.

-To help us provide seamless embedding creations throughout the experiment, we will use Qdrant’s native embedding provider [Fastembed]([https://qdrant.github.io/fastembed/](https://qdrant.github.io/fastembed/)) which supports [many different models]([https://qdrant.github.io/fastembed/examples/Supported_Models/](https://qdrant.github.io/fastembed/examples/Supported_Models/)) including dense as well as sparse vector models.
+To help us provide seamless embedding creations throughout the experiment, we will use Qdrant’s native embedding provider [Fastembed](https://qdrant.github.io/fastembed/) which supports [many different models](https://qdrant.github.io/fastembed/examples/Supported_Models/) including dense as well as sparse vector models.

 We can initialize and switch the embedding model of our choice as below :

@@ -32,7 +32,7 @@ POST collections/site/points/search
 }
 ```

-Even with avoiding a network round-trip, the embedding still takes some time. As always in optimization, if you cannot do the work faster, a good solution is to avoid work altogether (please don't tell my employer). This can be done by pre-computing common prefixes and calculating embeddings for them, then storing them in a `prefix_cache` collection. Now the [`recommend`](https://docs.rs/qdrant-client/latest/qdrant_client/client/struct.QdrantClient.html#method.recommend) API method can find the best matches without doing any embedding. For now, I use short (up to and including 5 letters) prefixes, but I can also parse the logs to get the most common search terms and add them to the cache later.
+Even with avoiding a network round-trip, the embedding still takes some time. As always in optimization, if you cannot do the work faster, a good solution is to avoid work altogether (please don't tell my employer). This can be done by pre-computing common prefixes and calculating embeddings for them, then storing them in a `prefix_cache` collection. Now the [`recommend`](https://api.qdrant.tech/api-reference/search/recommend-points) API method can find the best matches without doing any embedding. For now, I use short (up to and including 5 letters) prefixes, but I can also parse the logs to get the most common search terms and add them to the cache later.

 ![Qdrant Recommendation](/articles_data/search-as-you-type/Qdrant_Recommendation.png)

@@ -26,7 +26,7 @@ At Qdrant, we are happy to announce the successful completion our the SOC 2 Type

 ## SOC 2 Type II: What Is It?

-SOC 2 Type II certification is an examination of an organization's controls in reference to the American Institute of Certified Public Accountants [(AICPA) Trust Services criteria](https://www.aicpa-cima.com/content/dam/aicpa/interestareas/frc/assuranceadvisoryservices/downloadabledocuments/trust-services-criteria.pdf). It evaluates not only our written policies but also their practical implementation, ensuring alignment between our stated objectives and operational practices. Unlike Type I, which is a snapshot in time, Type II verifies over several months that the company has lived up to those controls. The report represents thorough auditing of our security procedures throughout this examination period: January 1, 2024 to April 7, 2024. 
+SOC 2 Type II certification is an examination of an organization's controls in reference to the American Institute of Certified Public Accountants [(AICPA) Trust Services criteria](https://www.aicpa-cima.com/resources/download/2017-trust-services-criteria-with-revised-points-of-focus-2022). It evaluates not only our written policies but also their practical implementation, ensuring alignment between our stated objectives and operational practices. Unlike Type I, which is a snapshot in time, Type II verifies over several months that the company has lived up to those controls. The report represents thorough auditing of our security procedures throughout this examination period: January 1, 2024 to April 7, 2024. 


 ## Key Audit Findings
@@ -11,7 +11,7 @@ aliases: [ ../integrations/cheshire-cat/ ]

 ## Cheshire Cat and Qdrant

-Cheshire Cat uses Qdrant as the default [Vector Memory](https://cheshire-cat-ai.github.io/docs/conceptual/memory/vector_memory/) for ingesting and retrieving documents.
+Cheshire Cat uses Qdrant as the default [Vector Memory](https://cheshire-cat-ai.github.io/docs/faq/llm-concepts/vector-memory/) for ingesting and retrieving documents.

 ```
 # Decide host and port for your Cat. Default will be localhost:1865
@@ -135,11 +135,7 @@ To search with only sparse vectors,

 The `langchain-qdrant` package provides a [FastEmbed](https://github.com/qdrant/fastembed) based implementation out of the box.

-To use it, install the FastEmbed package.
-
-```sh
-pip install fastembed
-```
+To use it, install the [FastEmbed package](https://github.com/qdrant/fastembed#-installation).

 ```python
 from langchain_qdrant import FastEmbedSparse, RetrievalMode
@@ -166,7 +162,25 @@ To perform a hybrid search using dense and sparse vectors with score fusion,
 - A [dense embeddings](https://python.langchain.com/v0.2/docs/integrations/text_embedding/) value should be provided for the `embedding` parameter.
 - An implementation of the [SparseEmbeddings interface](https://github.com/langchain-ai/langchain/blob/master/libs/partners/qdrant/langchain_qdrant/sparse_embeddings.py) using any sparse embeddings provider has to be provided as value to the `sparse_embedding` parameter.

-Note that if you've added documents with the HYBRID mode, you can switch to any retrieval mode when searching. Since both the dense and sparse vectors are available in the collection.
+```python
+from langchain_qdrant import FastEmbedSparse, RetrievalMode
+
+sparse_embeddings = FastEmbedSparse(model_name="Qdrant/bm25")
+
+qdrant = QdrantVectorStore.from_documents(
+    docs,
+    embedding=embeddings,
+    sparse_embedding=sparse_embeddings,
+    location=":memory:",
+    collection_name="my_documents",
+    retrieval_mode=RetrievalMode.HYBRID,
+)
+
+query = "What did the president say about Ketanji Brown Jackson"
+found_docs = qdrant.similarity_search(query)
+```
+
+Note that if you've added documents with HYBRID mode, you can switch to any retrieval mode when searching. Since both the dense and sparse vectors are available in the collection.

 ## Next steps

@@ -66,4 +66,4 @@ You can now use the `VectorStore` instance backed by Qdrant as a vector store in

 - Spring AI [Qdrant reference](https://docs.spring.io/spring-ai/reference/api/vectordbs/qdrant.html)
 - Spring AI [API reference](https://docs.spring.io/spring-ai/reference/index.html)
- [Source Code](https://github.com/spring-projects/spring-ai/tree/main/vector-stores/spring-ai-qdrant)
+- [Source Code](https://github.com/spring-projects/spring-ai/tree/main/vector-stores/spring-ai-qdrant-store)